December 12th, 2023 
Daniela Lopez de Luise If you are having trouble reading this message, click here for the web version.
IEEE AR e-Notice
Información para socios IEEE de la Sección Argentina
12 de diciembre de 2023
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
IEEE AR ComSoc – Conferencia “Federated Learning for Bandwidth Efficiency and Privacy in 6G and Future Networks”
Profesor Zhi Ding, IEEE Fellow – Miércoles 13 de diciembre 2023, 18:30, FIUBA (CABA)
El Capítulo Argentino de la IEEE Communications Society (ComSoc) y la Facultad de Ingeniería de la UBA (FIUBA) invitan a la conferencia sobre “Federated Learning for Bandwidth Efficiency and Privacy in 6G and Future Networks” que brindará el Profesor Zhi Ding, IEEE Fellow y Distinguished Professor del Department of Electrical and Computer Engineering, University of California, Davis (USA).
La misma se realizará el miércoles 13 de diciembre de 2023, a partir de las 18:30 AR (UTC-3), en el Aula 301, Tercer Piso, FIUBA, Av. Paseo Colón 850, CABA.
Resumen
Federated Learning (FL) has emerged as an effective paradigm for distributed learning systems owing to its strong potential to exploit underlying data characteristics while preserving data privacy. Many existing solutions advocate the highly inefficient gradient sharing that is neither efficient nor secure.
This talk introduces two federated learning paradigms in future wireless networks that are bandwidth efficient and provide strong privacy.
The first proposal is a novel FL framework that only applies partial GAN model sharing. This new PS-FedGAN framework effectively addresses heterogeneous data distributions across
clients and strengthens privacy preservation at reduced communication costs, especially over wireless networks.
Our analysis demonstrates the convergence and privacy benefits of the proposed PS-FedGAN framework.
The second design innovates a novel over-the-air soft information aggregation for collaborative decision-making over distributed sensing networks. We exploit the natural superposition of wireless transmissions to enable sensors to utilize over-the-air computation to approximate the sufficient statistic for optimum detection over a shared channel. By designing practical transmission and receiver processing in over-the-air computation, the decision-making fusion server can wirelessly obtain a good approximation of the aggregate log-likelihood ratio computed over all observed data with low distortion.
Our results show significant over-the-air collaboration gain even with a few participating nodes. The novel framework exhibits very little performance loss of detection accuracy against traditional multiple access transmission from sensing nodes despite substantial resource savings over-the-air computation.
Disertante
Dr. Zhi Ding is a distinguished professor in the Department of Electrical and Computer Engineering at the University of California, Davis (USA).
He received his Ph.D. degree in Electrical Engineering from Cornell University in 1990.
From 1990 to 2000, he was a faculty member of Auburn University, later of the University of Iowa, and joined the College of Engineering at UC Davis in 2000.
His major research interests and expertise cover the areas of wireless networking,
communications, signal processing, multimedia, and learning.
He coauthors the textbook: Modern Digital and Analog Communication Systems, 5th edition, Oxford University Press, 2019.
At IEEE, he was a Distinguished Lecturer (Circuits and Systems Society, 2004-06, Communications Society, 2008-09) and served as IEEE Transactions on Wireless Communications Steering Committee Member (2007-2009) and its Chair (2009-2010).
He received the IEEE Communication Society WTC Award in 2012 and the IEEE Communication Society Education Award in 2020.
– – – – – – – – – –
Muchas gracias por su atención.
IEEE Argentina
* * *
Posted in